The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script resolve_customization.py using uv run during both the activation and completion phases to handle configuration merging and finalization logic. These scripts are located within the project's internal directory structure ({project-root}/_bmad/scripts/).
[PROMPT_INJECTION]: The workflow incorporates data from multiple external sources, including user responses and external files specified via globs, which are interpolated into the strategic analysis prompts without explicit sanitization or escaping.
Ingestion points: User input in Step 1, file-based facts in Step 3, and configuration values from config.yaml in Step 4.
Boundary markers: The skill uses markdown headers and specific XML-style tags (<template-output>) to structure the workflow, providing some inherent structure, but lacks explicit guardrail instructions to ignore potential commands within the ingested data.
Capability inventory: The agent has the capability to write to the filesystem ({default_output_file}), read arbitrary project files via persistent_facts, and execute local shell commands via uv run.
Sanitization: No sanitization or validation logic is applied to the ingested external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The module-manifest.toml references the vendor's GitHub repository for updates and an external documentation site. Both github.com/bmad-code-org and bmad-method.org are legitimate vendor-controlled domains.

bmad-cis-innovation-strategy